CVE-2026-24271 Denial of service in TensorRT-LLM
An attacker can exhaust GPU resources via the OpenAI-compatible API, causing denial of service in NVIDIA TensorRT-LLM deployments.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-24271?
CVE-2026-24271 is a medium-severity denial of service vulnerability in NVIDIA TensorRT-LLM, published on 14 Jul 2026. It can only be exploited from the same machine or local network, with no action from the victim.
Official description
NVIDIA TensorRT-LLM contains a vulnerability in the OpenAI-compatible inference API, where an attacker could cause allocation of GPU resources without limits or throttling. A successful exploit of this vulnerability might lead to denial of service.
Weakness: CWE-770
Which versions are affected by CVE-2026-24271?
How do I fix CVE-2026-24271?
No fix has been published for CVE-2026-24271 yet. Limit exposure of the affected software until one is available.
Upgrade, then put limits on request size, rate and nesting depth so one client cannot exhaust the service. More about Denial of service.
Is CVE-2026-24271 being exploited?
There is no known exploitation of CVE-2026-24271 in the wild and no public exploit code.
Sources
Also known as GHSA-3wc9-fv9q-6v3m.